Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88334
    Prev
    Next
    INDEX
    Explanations

    conversational and web text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cleverly
    -0.08
     farther
    -0.08
    Honestly
    -0.08
    yak
    -0.08
     RUB
    -0.07
     അവസ
    -0.07
    塑
    -0.07
     wodurch
    -0.07
     beek
    -0.07
     geothermal
    -0.07
    POSITIVE LOGITS
    orra
    0.08
     vote
    0.07
    岗
    0.07
     submet
    0.07
    �
    0.07
     Shaw
    0.07
    Vote
    0.07
    .vote
    0.07
    :maj
    0.07
    /of
    0.07
    Activations Density 0.000%

    No Known Activations